Machine learning-based diagnosis of autism spectrum disorder in children using eye-tracking data: a systematic review and meta-analysis

A systematic review and meta-analysis of 25 studies evaluated machine learning models applied to eye-tracking data for distinguishing children with ASD from typically developing peers, involving 2,319 participants across studies. The pooled analysis found ML models achieved 85% accuracy, 86% sensitivity, and high specificity in detecting ASD from eye-tracking patterns.